© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 127830
    Prev
    Next
    INDEX
    Explanations

    references to sand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hanging
    -0.07
    s
    -0.06
    /pub
    -0.06
    inç
    -0.06
    -minded
    -0.06
    abaj
    -0.06
    stal
    -0.06
     Ñĥж
    -0.06
     damned
    -0.06
    /account
    -0.06
    POSITIVE LOGITS
    æ²Ļ
    0.08
    _ROUT
    0.08
    igger
    0.07
    iegel
    0.07
    ĵåIJį
    0.07
    íĨłíĨł
    0.07
    hya
    0.07
    stone
    0.07
    kker
    0.07
    istrovstvÃŃ
    0.07
    Activations Density 0.009%

    No Known Activations